Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System

Mar 21, 20128 likes2,032 views

Daniel Gallego Vico

Research work presented by Daniel Gallego at the International Conference on Digital Society 2012 at Valencia, Spain

Generating Context-aware
Recommendations
using Banking Data in a
Mobile Recommender System
Daniel Gallego
Gabriel Huecas
Joaquín Salvachúa

ICDS 2012

Background

• Traditional recommender systems are based
on subjective data:
– Personal scores, biased tastes, etc.
– This causes a trust problem in the results

• New eBusiness applications:
– Use recommendation features based on real
purchases (e.g. Amazon)
– Increase confidence
2

Research Motivation

• Banks have rich information about:
– Customer purchases and profiles
– Economic trends

• We propose a model to generate
recommendations about places
– A place is any entity where bank clients have paid
with their credit cards

3

Personalized Recommendation Process
Social Context
• Based on generating Generation

context-awareness User’s Cluster Trends Map
information:
– Social context Location Context
Filtering
previously generated
– Location and User Geo-located User’s Cluster Trends Map
context generated in
real time User Context
Filtering

Personalized Recommendation 4

Personalized Recommendation Process
Social Context
Generation

User’s Cluster Trends Map

Location Context
Filtering

Geo-located User’s Cluster Trends Map

User Context
Filtering

Personalized Recommendation 5

Location Context
Mobile Context
Devices Information

User’s
Location
Acquisition
User’s
Location

User’s
Location
Cluster
Trends
based
Map Filtering

Geo-Located
User’s Cluster
Trends Map 8

User Context
Lunch time
Restaurants category Geo-Located
User’s
Cluster Trends
Map

User Ranking
Context Generation

Personalized
Recommendation

10

Social Clusters: Evaluation

• Model tested in a collaboration with an
important Spanish bank

• Banking data provided with information on:
– 2.5 million credit card transactions
– 222,000 places information
– 34,000 anonymous customer’s profiles between
48 and 55 years old

11

Social Clusters: Results
70000
expense in one year (€) Circle diameter
equivalent to
60000
Average credit card

Social Cluster size
50000

40000

30000

20000

10000

0
46 48 50 52 54 56
-10000
Average age 12

User acceptance: Evaluation

• System deployed in the bank Labs
– Secure environment

• Android Mobile prototype developed
– Allow customers to test the application

• Online survey:
– 100 bank customers
– 2 scenarios: restaurants and supermarkets
– Several properties evaluated in a Likert scale
– Comments provided by test users
13

User Acceptance: Results
• Overall positive attitude towards the system
– High confidence in the recommendations
• Users remarked privacy issues related to a real
commercial exploitation
5

4

3

2

1

0
Convenient Desirable Effective Reliable Useful
14

Conclusions
• Model proposed to generate:
– Context-aware recommendations
– Using banking data
– In mobile systems

• Mobile prototype developed successfully in the
Bank Labs environment

• High confidence in the personalized
recommendations generated:
– Because of the banking data used

15

Future Work

• Proactivity:
– The system pushes recommendations to the user
– When current situation seems appropriate
– Without user explicit request

• Multiple personalities in the system
– “What kind of customer do you want to be today?”
– Several profiles with different social clusters
associated

16

Thank you!
Questions?
Daniel Gallego
@thanos_malkav
dgallego@dit.upm.es
http://danielgallegovico.es

1) The document proposes methods for incorporating proactivity into mobile context-aware recommender systems (CARS) and evaluates their impact on user experience. 2) An architecture is presented for building social mobile CARS that integrates various social data sources while addressing privacy, cross-platform use, and cold start issues. 3) A model is described for generating proactive recommendations in mobile CARS based on assessing the appropriateness of the user's situation and suitability of item recommendations.

Presentation: An Introduction to IdeaScaleIdeaScale

��

IdeaScale is a cloud-based innovation platform that allows organizations to crowdsource ideas from large communities. It has over 25,000 communities and 4 million users. The platform offers secure idea submission, voting, commenting and tracking across multiple clients including 20% of Fortune 100 companies and 25 federal agencies. It provides various tools for administrators to customize, launch challenges, and analyze idea trends and outcomes.

Managing Online Business CommunitiesSteffen Staab

��

1) The ROBUST project aims to develop techniques for analyzing and managing online business communities. This includes identifying risks, opportunities, and the impacts of policy changes through community simulation. 2) Key techniques include community analysis to detect trends like user churn, content analysis to discover interesting content, and indexing distributed semantic graphs from linked open data to enable querying across data sources. 3) The lessons learned are that business communities vary and require novel analysis techniques like integration of different data sources, simulation of policy changes, and assessment of user value. External companies were interested in this type of community management technology.

Recommender systems in the scope of opinion formation: a modelMarcel Blattner, PhD

��

1. The document proposes a model to simulate recommendation systems data featuring fat-tailed distributions of item ratings. 2. The model is based on social interactions and opinion formation on a complex network. A threshold mechanism governs whether a user is interested in an item based on their intrinsic item anticipation and influence from neighbors. 3. The model can generate various patterns observed in real recommendation systems data and provides insight into how social processes shape recommender system data.

A contextual bandit algorithm for mobile context-aware recommender systemBouneffouf Djallel

��

Most existing approaches in Mobile Context-Aware Recommender Systems focus on recommending relevant items to users taking into account contextual information, such as time, location, or social aspects. However, none of them has considered the problem of user’s content evolution. We introduce in this paper an algorithm that tackles this dynamicity. It is based on dynamic exploration/exploitation and can adaptively balance the two aspects by deciding which user’s situation is most relevant for exploration or exploitation. Within a deliberately designed offline simulation framework we conduct evaluations with real online event log data. The experimental results demonstrate that our algorithm outperforms surveyed algorithms.

Contextual Bandit SurveySangwoo Mo

��

Multi Armed Bandits and Optimized Online MarketingMarkus Ojala

��

Data-Driven Recommender Systemsrecsysfr

��

The document discusses recommender systems and sequential recommendation problems. It covers several key points: 1) Matrix factorization and collaborative filtering techniques are commonly used to build recommender systems, but have limitations like cold start problems and how to incorporate additional constraints. 2) Sequential recommendation problems can be framed as multi-armed bandit problems, where past recommendations influence future recommendations. 3) Various bandit algorithms like UCB, Thompson sampling, and LinUCB can be applied, but extending guarantees to models like matrix factorization is challenging. Offline evaluation on real-world datasets is important.

3D context-aware mobile maps for tourism - ENTER2011 PhD WorkshopZornitza Yovcheva

��

This is the presentation I delivered at ENTER2011 presenting the work I started with at the John Kent Institute in Tourism, Bournemouth University. The proposal I submitted there won the first prize of the PhD Workshop. Even though my ideas have changed since then I really like this presentation as it explains what I was planning to focus on then - three dimensional maps and how we can make them more context aware and adaptive.

Big Data Analytics Insights Conference- SatnamSatnam Singh

��

Mobile data analytics is still in the early stages of development but brings opportunities for innovative new features in smartphones and transforming businesses. Future mobile devices will be built on analytics platforms to deliver intelligent, personalized, and context-aware features. Virtual assistants, text, image, video, gesture, and multi-model analytics were discussed along with trends and enabling technologies in each area.

Social Computing ResearchUCL-CS MobiSys

��

This document outlines an upcoming MOBISYS seminar on social computing research. The seminar will feature 4-minute presentations from 4 speakers: Licia Capra, Afra Mashadi, Claudio Weeraratne, and Valentina Zanardi. Additional researchers may also present. The speakers will discuss their work on topics like collaborative filtering, reputation systems, trust models, content sharing, and analyzing social behavior in pervasive computing environments. Future directions for research are also mentioned.

Activity-Based Serendipitous Recommendations with the Magitti Mobile Leisure ...bo begole

��

This paper presents a context-aware mobile recommender system, codenamed Magitti. Magitti is unique in that it infers user activity from context and patterns of user behavior and, without its user having to issue a query, automatically generates recommendations for content matching. Extensive field studies of leisure time practices in an urban setting (Tokyo) motivated the idea, shaped the details of its design and provided data describing typical behavior patterns. The paper describes the fieldwork, user interface, system components and functionality, and an evaluation of the Magitti prototype.

Managing dynamiccontext 2010-06_lillev2norhavillegas

��

Norha Villegas is a first year PhD student at the University of Victoria researching context management for self-adaptive systems. Her research group, Rigi, investigates methods and techniques for supporting autonomic and self-managing systems. She is currently working on a project with IBM to manage dynamic context to optimize smart interactions and services on the smart internet. Some key challenges include developing dynamic context models and infrastructures to gather and use context information.

OmniSuggest: A Ubiquitous Cloud-Based Context-Aware Recommendation System for...Joshwa Philip

��

(1) The document proposes OmniSuggest, a context-aware recommendation system for mobile social networks. (2) OmniSuggest utilizes a combination of collaborative filtering and social computing techniques to provide personalized venue recommendations to both individual users and groups. (3) It addresses limitations of existing systems like data sparsity and cold start problems through a cloud-based architecture that ranks users and venues and creates similarity graphs.

Social Localisation - What's your messageThe Rosetta Foundation

��

��100621��젵ӕ�발표DongKyun Lee

��

Here are 3 users selected based on their location history in Kang-nam, Seoul: A - Has visited Kang-nam area at least once a week for the past 3 months. Currently lives nearby. C - Restaurant reviewer who frequently dines around Kang-nam for work. Was there last weekend. D - Often goes to Kang-nam after work to meet friends. Checked in at a cafe there yesterday. Re-ranking process of Aardwolf Gateway Query : “where is the best Japanese Ramen restaurant in Kang-nam, Seoul ?” Location Location history Manager Routing Engine 2. Rank users by algorithm of Aardwolf 3. Re-

Communities for Innovation Engaged Organizations

��

Reflect network meeting (13/07/2012)Reflect Project

��

The document discusses a research project that uses a smartphone app to collect subjective travel experience data from individuals. The app will provide feedback to users about their own experiences as well as those of others. The researchers aim to see if these interventions can change travel behaviors and reduce emissions. They will draw on theories from behavioral economics, psychology, and technology acceptance. An important goal is to pilot and refine the app to make it more usable and understand its impact on travel choices over multiple trials involving both strangers and friends.

Social networking text mining - analytics in km 13.dec.2011HCL Technologies

��

This document discusses using social software and networking to improve knowledge management (KM) processes. It provides examples of how social networking can connect people to share knowledge and solve problems more efficiently than via email. Communities of practice are proposed as social networks to learn, prioritize, validate, publish and apply information. Text mining and analytics can be applied to gather, process and analyze content within these networks. Dashboards and tagging allow insights to be surfaced and applied. Overall, the document argues that social networking combined with text mining and analytics can deliver business value by improving knowledge sharing and enabling faster solutions to issues.

Harvesting Intelligence from User Interactions R A Akerkar

��

This document discusses how to harvest intelligence from user interactions on websites. It explains that as users share opinions, content, and participate in online communities, data is generated that can be converted into intelligence to personalize websites. It describes how collecting diverse opinions from many users can lead to "wise crowds" and collective intelligence. The key is to allow user interactions, learn about users in aggregate, and personalize content using this data. Content and collaborative filtering are approaches to build user and item profiles to detect meaningful relationships and make recommendations. The goal is to transform applications from being content-centric to being user-centric using collective intelligence.

VC Do's and Don'ts - Jurgen Ingels Frank Gielen

��

This document discusses Clear2Pay's financing and reporting. It provides background on Jürgen Ingels and an overview of Clear2Pay and NGDATA, including their histories, products/services, clients, and growth. It also covers fundraising best practices and challenges in communicating financials to non-financial stakeholders. Key points include Clear2Pay's expansion globally and into new payments products and services over time, and NGDATA's focus on using big data to drive customer loyalty and intelligence. Fundraising tips emphasize preparation, choosing investors wisely, and negotiating terms favorably.

Context Adaptive ServicesJohn Yanosy Jr

��

Attlassian Summit: SunSpacePeter H. Reiser

��

1) The document describes SunSpace, a concept and architecture for building vibrant communities within organizations by focusing on people and promoting participation. 2) Key aspects of SunSpace include calculating "community equity" to promote participation, integrating with existing knowledge bases, and satisfying individual needs to promote sharing. 3) The SunSpace architecture includes services for communities, content sharing, search, and user profiles to bring people and information together.

Embracing & Sustaining Your Community EcosystemDell Social Media

��

Experiences in the Design and Implementation of a Social Cloud for Volunteer ...ryanchard

��

This document proposes a "Social Cloud for Volunteer Computing" (SoCVC) to address barriers that volunteer computing projects face in user discovery, engagement, and accountability. It describes how a SoCVC could leverage social networks like Facebook to connect 1% of users to BOINC, increasing eScience resources tremendously compared to current levels. The authors implemented a Facebook application to prototype the SoCVC concept and test performance. Simulation results showed how social incentives like titles for high contributors could encourage increased contribution over time through social influence within networks. An upcoming full release of the SoCVC is planned for late 2012.

Maponics neighborhood-boundaries-ps-012711Maponics

��

Maponics provides neighborhood boundary data for over 59 countries collected from multiple local sources and validated using quality assurance processes. Their comprehensive dataset includes unambiguous neighborhood boundaries, classifications, and hierarchies. This neighborhood data allows customers to search and display real estate, businesses, and points of interest at the neighborhood level, improving search relevancy and enabling targeted marketing by neighborhood demographics.

GeniUS: Generic User Modeling Library for the Social Semantic WebWeb Information Systems, TU Delft

��

GeniUS is a topic and user modeling library that produces semantically meaningful user profiles from social web data to enhance interoperability between applications. It aggregates relevant user information from sources like Twitter, enriches it with semantic data, and generates customized profiles according to application needs. Evaluation shows domain-specific profiles generated by GeniUS improve recommendation performance compared to generic profiles, with performance varying slightly between domains.

MoveSmart.org Overviewjustingmassa

��

This document provides an overview of MoveSmart.org, a technology platform that aims to encourage residential integration and rebuild social capital through a housing search tool. The tool would leverage data and an intuitive interface to help users find neighborhoods that match their priorities. Features would include neighborhood guides, a neighborhood finder tool, user stories, and tools to connect users to local organizations. The platform is designed to be cost-effective, modular, and help overcome barriers to integration like a lack of information. It has received interest from foundations and is peer-vetted.

Formal Methods: Whence and Whither? [Martin Fränzle Festkolloquium, 2025]Jonathan Bowen

��

Alan Turing arguably wrote the first paper on formal methods 75 years ago. Since then, there have been claims and counterclaims about formal methods. Tool development has been slow but aided by Moore’s Law with the increasing power of computers. Although formal methods are not widespread in practical usage at a heavyweight level, their influence as crept into software engineering practice to the extent that they are no longer necessarily called formal methods in their use. In addition, in areas where safety and security are important, with the increasing use of computers in such applications, formal methods are a viable way to improve the reliability of such software-based systems. Their use in hardware where a mistake can be very costly is also important. This talk explores the journey of formal methods to the present day and speculates on future directions.

EaseUS Partition Master Crack 2025 + Serial Keykherorpacca127

��

https://ncracked.com/7961-2/ Note: >> Please copy the link and paste it into Google New Tab now Download link EASEUS Partition Master Crack is a professional hard disk partition management tool and system partition optimization software. It is an all-in-one PC and server disk management toolkit for IT professionals, system administrators, technicians, and consultants to provide technical services to customers with unlimited use. EASEUS Partition Master 18.0 Technician Edition Crack interface is clean and tidy, so all options are at your fingertips. Whether you want to resize, move, copy, merge, browse, check, convert partitions, or change their labels, you can do everything with a few clicks. The defragmentation tool is also designed to merge fragmented files and folders and store them in contiguous locations on the hard drive.

More Related Content

Similar to Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System (20)

3D context-aware mobile maps for tourism - ENTER2011 PhD WorkshopZornitza Yovcheva

��

Big Data Analytics Insights Conference- SatnamSatnam Singh

��

Social Computing ResearchUCL-CS MobiSys

��

Activity-Based Serendipitous Recommendations with the Magitti Mobile Leisure ...bo begole

��

Managing dynamiccontext 2010-06_lillev2norhavillegas

��

OmniSuggest: A Ubiquitous Cloud-Based Context-Aware Recommendation System for...Joshwa Philip

��

Social Localisation - What's your messageThe Rosetta Foundation

��

��100621��젵ӕ�발표DongKyun Lee

��

Communities for Innovation Engaged Organizations

��

Reflect network meeting (13/07/2012)Reflect Project

��

Social networking text mining - analytics in km 13.dec.2011HCL Technologies

��

Harvesting Intelligence from User Interactions R A Akerkar

��

VC Do's and Don'ts - Jurgen Ingels Frank Gielen

��

Context Adaptive ServicesJohn Yanosy Jr

��

Attlassian Summit: SunSpacePeter H. Reiser

��

Embracing & Sustaining Your Community EcosystemDell Social Media

��

Experiences in the Design and Implementation of a Social Cloud for Volunteer ...ryanchard

��

Maponics neighborhood-boundaries-ps-012711Maponics

��

GeniUS: Generic User Modeling Library for the Social Semantic WebWeb Information Systems, TU Delft

��

MoveSmart.org Overviewjustingmassa

��

3D context-aware mobile maps for tourism - ENTER2011 PhD WorkshopZornitza Yovcheva

��

Big Data Analytics Insights Conference- SatnamSatnam Singh

��

Social Computing ResearchUCL-CS MobiSys

��

Activity-Based Serendipitous Recommendations with the Magitti Mobile Leisure ...bo begole

��

Managing dynamiccontext 2010-06_lillev2norhavillegas

��

OmniSuggest: A Ubiquitous Cloud-Based Context-Aware Recommendation System for...Joshwa Philip

��

Social Localisation - What's your messageThe Rosetta Foundation

��

��100621��젵ӕ�발표DongKyun Lee

��

Communities for Innovation Engaged Organizations

��

Reflect network meeting (13/07/2012)Reflect Project

��

Social networking text mining - analytics in km 13.dec.2011HCL Technologies

��

Harvesting Intelligence from User Interactions R A Akerkar

��

VC Do's and Don'ts - Jurgen Ingels Frank Gielen

��

Context Adaptive ServicesJohn Yanosy Jr

��

Attlassian Summit: SunSpacePeter H. Reiser

��

Embracing & Sustaining Your Community EcosystemDell Social Media

��

Experiences in the Design and Implementation of a Social Cloud for Volunteer ...ryanchard

��

Maponics neighborhood-boundaries-ps-012711Maponics

��

GeniUS: Generic User Modeling Library for the Social Semantic WebWeb Information Systems, TU Delft

��

MoveSmart.org Overviewjustingmassa

��

Recently uploaded (20)

Formal Methods: Whence and Whither? [Martin Fränzle Festkolloquium, 2025]Jonathan Bowen

��

EaseUS Partition Master Crack 2025 + Serial Keykherorpacca127

��

Technology use over time and its impact on consumers and businesses.pptxkaylagaze

��

DevNexus - Building 10x Development Organizations.pdfJustin Reock

��

Developer Experience is Dead! Long Live Developer Experience! In this keynote-style session, we’ll take a detailed, granular look at the barriers to productivity developers face today and modern approaches for removing them. 10x developers may be a myth, but 10x organizations are very real, as proven by the influential study performed in the 1980s, ‘The Coding War Games.’ Right now, here in early 2025, we seem to be experiencing YAPP (Yet Another Productivity Philosophy), and that philosophy is converging on developer experience. It seems that with every new method, we invent to deliver products, whether physical or virtual, we reinvent productivity philosophies to go alongside them. But which of these approaches works? DORA? SPACE? DevEx? What should we invest in and create urgency behind today so we don’t have the same discussion again in a decade?

Stronger Together: Combining Data Quality and Governance for Confident AI & A...Precisely

��

SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOTTanmaiArni

��

UiPath Agentic Automation Capabilities and OpportunitiesDianaGray10

��

Learn what UiPath Agentic Automation capabilities are and how you can empower your agents with dynamic decision making. In this session we will cover these topics: What do we mean by Agents Components of Agents Agentic Automation capabilities What Agentic automation delivers and AI Tools Identifying Agent opportunities ❓ If you have any questions or feedback, please refer to the "Women in Automation 2025" dedicated Forum thread. You can find there extra details and updates.

World Information Architecture Day 2025 - UX at a CrossroadsJoshua Randall

��

User Experience stands at a crossroads: will we live up to our potential to design a better world? or will we be co-opted by “product management” or another business buzzword? Looking backwards, this talk will show how UX has repeatedly failed to create a better world, drawing on industry data from Nielsen Norman Group, Baymard, MeasuringU, WebAIM, and others. Looking forwards, this talk will argue that UX must resist hype, say no more often and collaborate less often (you read that right), and become a true profession — in order to be able to design a better world.

UiPath Automation Developer Associate Training Series 2025 - Session 2DianaGray10

��

In session 2, we will introduce you to Data manipulation in UiPath Studio. Topics covered: Data Manipulation What is Data Manipulation Strings Lists Dictionaries RegEx Builder Date and Time Required Self-Paced Learning for this session: Data Manipulation with Strings in UiPath Studio (v2022.10) 2 modules - 1h 30m - https://academy.uipath.com/courses/data-manipulation-with-strings-in-studio Data Manipulation with Lists and Dictionaries in UiPath Studio (v2022.10) 2 modules - 1h - https:/academy.uipath.com/courses/data-manipulation-with-lists-and-dictionaries-in-studio Data Manipulation with Data Tables in UiPath Studio (v2022.10) 2 modules - 1h 30m - https:/academy.uipath.com/courses/data-manipulation-with-data-tables-in-studio ⁉️ For any questions you may have, please use the dedicated Forum thread. You can tag the hosts and mentors directly and they will reply as soon as possible.

Backstage Software Templates for Java DevelopersMarkus Eisele

��

Replacing RocksDB with ScyllaDB in Kafka Streams by Almog GavraScyllaDB

��

Transform Your Future with Front-End Development TrainingVtechlabs

��

Kickstart your career in web development with our front-end web development course in Vadodara. Learn HTML, CSS, JavaScript, React, and more through hands-on projects and expert mentorship. Our front-end development course with placement includes real-world training, mock interviews, and job assistance to help you secure top roles like Front-End Developer, UI/UX Developer, and Web Designer. Join VtechLabs today and build a successful career in the booming IT industry!

The Future of Repair: Transparent and Incremental by Botond DénesScyllaDB

��

Regularly run repairs are essential to keep clusters healthy, yet having a good repair schedule is more challenging than it should be. Repairs often take a long time, preventing running them often. This has an impact on data consistency and also limits the usefulness of the new repair based tombstone garbage collection. We want to address these challenges by making repairs incremental and allowing for automatic repair scheduling, without relying on external tools.

L01 Introduction to Nanoindentation - What is hardnessRostislavDaniel

��

Field Device Management Market Report 2030 - TechSci ResearchVipin Mishra

��

The Global Field Device Management (FDM) Market is expected to experience significant growth in the forecast period from 2026 to 2030, driven by the integration of advanced technologies aimed at improving industrial operations. 📊 According to TechSci Research, the Global Field Device Management Market was valued at USD 1,506.34 million in 2023 and is anticipated to grow at a CAGR of 6.72% through 2030. FDM plays a vital role in the centralized oversight and optimization of industrial field devices, including sensors, actuators, and controllers. Key tasks managed under FDM include: Configuration Monitoring Diagnostics Maintenance Performance optimization FDM solutions offer a comprehensive platform for real-time data collection, analysis, and decision-making, enabling: Proactive maintenance Predictive analytics Remote monitoring By streamlining operations and ensuring compliance, FDM enhances operational efficiency, reduces downtime, and improves asset reliability, ultimately leading to greater performance in industrial processes. FDM’s emphasis on predictive maintenance is particularly important in ensuring the long-term sustainability and success of industrial operations. For more information, explore the full report: https://shorturl.at/EJnzR Major companies operating in Global��Field Device Management Market are: General Electric Co Siemens AG ABB Ltd Emerson Electric Co Aveva Group Ltd Schneider Electric SE STMicroelectronics Inc Techno Systems Inc Semiconductor Components Industries LLC International Business Machines Corporation (IBM) #FieldDeviceManagement #IndustrialAutomation #PredictiveMaintenance #TechInnovation #IndustrialEfficiency #RemoteMonitoring #TechAdvancements #MarketGrowth #OperationalExcellence #SensorsAndActuators

1.1. Evolution-and-Scope-of-Business-Analytics.pptxJitendra Tomar

��

30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...ScyllaDB

��

Endpoint Backup: 3 Reasons MSPs Ignore ItMSP360

��

Deno ...................................Robert MacLean

��

Unlock AI Creativity: Image Generation with DALL·EExpeed Software

��

Discover the power of AI image generation with DALL·E, an advanced AI model that transforms text prompts into stunning, high-quality visuals. This presentation explores how artificial intelligence is revolutionizing digital creativity, from graphic design to content creation and marketing. Learn about the technology behind DALL·E, its real-world applications, and how businesses can leverage AI-generated art for innovation. Whether you're a designer, developer, or marketer, this guide will help you unlock new creative possibilities with AI-driven image synthesis.

Formal Methods: Whence and Whither? [Martin Fränzle Festkolloquium, 2025]Jonathan Bowen

��

EaseUS Partition Master Crack 2025 + Serial Keykherorpacca127

��

Technology use over time and its impact on consumers and businesses.pptxkaylagaze

��

DevNexus - Building 10x Development Organizations.pdfJustin Reock

��

Stronger Together: Combining Data Quality and Governance for Confident AI & A...Precisely

��

SMART SENTRY CYBER THREAT INTELLIGENCE IN IIOTTanmaiArni

��

UiPath Agentic Automation Capabilities and OpportunitiesDianaGray10

��

World Information Architecture Day 2025 - UX at a CrossroadsJoshua Randall

��

UiPath Automation Developer Associate Training Series 2025 - Session 2DianaGray10

��

Backstage Software Templates for Java DevelopersMarkus Eisele

��

Replacing RocksDB with ScyllaDB in Kafka Streams by Almog GavraScyllaDB

��

Transform Your Future with Front-End Development TrainingVtechlabs

��

The Future of Repair: Transparent and Incremental by Botond DénesScyllaDB

��

L01 Introduction to Nanoindentation - What is hardnessRostislavDaniel

��

Field Device Management Market Report 2030 - TechSci ResearchVipin Mishra

��

1.1. Evolution-and-Scope-of-Business-Analytics.pptxJitendra Tomar

��

30B Images and Counting: Scaling Canva's Content-Understanding Pipelines by K...ScyllaDB

��

Endpoint Backup: 3 Reasons MSPs Ignore ItMSP360

��

Deno ...................................Robert MacLean

��

Unlock AI Creativity: Image Generation with DALL·EExpeed Software

��

Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System

1. Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System Daniel Gallego Gabriel Huecas Joaquín Salvachúa ICDS 2012

2. Background • Traditional recommender systems are based on subjective data: – Personal scores, biased tastes, etc. – This causes a trust problem in the results • New eBusiness applications: – Use recommendation features based on real purchases (e.g. Amazon) – Increase confidence 2

3. Research Motivation • Banks have rich information about: – Customer purchases and profiles – Economic trends • We propose a model to generate recommendations about places – A place is any entity where bank clients have paid with their credit cards 3

4. Personalized Recommendation Process Social Context • Based on generating Generation context-awareness User’s Cluster Trends Map information: – Social context Location Context Filtering previously generated – Location and User Geo-located User’s Cluster Trends Map context generated in real time User Context Filtering Personalized Recommendation 4

5. Personalized Recommendation Process Social Context Generation User’s Cluster Trends Map Location Context Filtering Geo-located User’s Cluster Trends Map User Context Filtering Personalized Recommendation 5

6. Social Context Banking User Profile Client Profiles Clustering Social Clusters Transactions Transactions and Places Assignment Clusters Trends Map Target User’s User Cluster Profile Discovery Target user User’s Cluster Trends 6 Map

7. Personalized Recommendation Process Social Context Generation User’s Cluster Trends Map Location Context Filtering Geo-located User’s Cluster Trends Map User Context Filtering Personalized Recommendation 7

8. Location Context Mobile Context Devices Information User’s Location Acquisition User’s Location User’s Location Cluster Trends based Map Filtering Geo-Located User’s Cluster Trends Map 8

9. Personalized Recommendation Process Social Context Generation User’s Cluster Trends Map Location Context Filtering Geo-located User’s Cluster Trends Map User Context Filtering Personalized Recommendation 9

10. User Context Lunch time Restaurants category Geo-Located User’s Cluster Trends Map User Ranking Context Generation Personalized Recommendation 10

11. Social Clusters: Evaluation • Model tested in a collaboration with an important Spanish bank • Banking data provided with information on: – 2.5 million credit card transactions – 222,000 places information – 34,000 anonymous customer’s profiles between 48 and 55 years old 11

12. Social Clusters: Results 70000 expense in one year (€) Circle diameter equivalent to 60000 Average credit card Social Cluster size 50000 40000 30000 20000 10000 0 46 48 50 52 54 56 -10000 Average age 12

13. User acceptance: Evaluation • System deployed in the bank Labs – Secure environment • Android Mobile prototype developed – Allow customers to test the application • Online survey: – 100 bank customers – 2 scenarios: restaurants and supermarkets – Several properties evaluated in a Likert scale – Comments provided by test users 13

14. User Acceptance: Results • Overall positive attitude towards the system – High confidence in the recommendations • Users remarked privacy issues related to a real commercial exploitation 5 4 3 2 1 0 Convenient Desirable Effective Reliable Useful 14

15. Conclusions • Model proposed to generate: – Context-aware recommendations – Using banking data – In mobile systems • Mobile prototype developed successfully in the Bank Labs environment • High confidence in the personalized recommendations generated: – Because of the banking data used 15

16. Future Work • Proactivity: – The system pushes recommendations to the user – When current situation seems appropriate – Without user explicit request • Multiple personalities in the system – “What kind of customer do you want to be today?” – Several profiles with different social clusters associated 16

17. Thank you! Questions? Daniel Gallego @thanos_malkav dgallego@dit.upm.es http://danielgallegovico.es

�ݺ�ߣ

Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System

Recommended

More Related Content

Similar to Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System (20)

Recently uploaded (20)

Generating Context-aware Recommendations using Banking Data in a Mobile Recommender System